Examples: Speech

Chichewa ASR via MMS-Large + Google Translate

4 runs

Transcribe any YouTube, mp3, WhatsApp audio or wavs with the best of transcription and translation AI models from OpenAI (Whisper v2 & v3), Microsoft Azure, Google USM, Meta Seemless4MT, AI4Bharat, Bhashini, etc Optionally translate to any language too.

Documents

🔗https://drive.google.com/file/d/1BhLCiVGYXTHYEe_lfxdr00R1aX0FRh8t/view?usp=drive_link

Transcription

Sean Blagsvedt

Kikuyu via MMS Large and GhanaNLP for Speech Reco & Trans

6 runs

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Documents

🔗https://drive.google.com/file/d/1s7SVHYEFmUAVUzGEFCeFahQv6GRRTT2l/view?pli=1

Transcription

Dev Aggrawal

Whisper Large v3 - Kannada

5 runs

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Documents

🔗3_audio_from_918247443697_to_112808001793652.wav

Transcription

Dev Aggrawal

Seamless M4T Kannada -> EN

3 runs

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Documents

🔗3_audio_from_918247443697_to_112808001793652.wav

Transcription

Dev Aggrawal

Google Cloud V1 - Swahili -> EN

2 runs

Documents

🔗WHATSAPP_audio_from_918764022384_to_113275925092502.wav

Transcription

Dev Aggrawal

Seamless M4T - Swahili -> EN

17 runs

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Documents

🔗WHATSAPP_audio_from_918764022384_to_113275925092502.wav

Transcription

Dev Aggrawal

Whisper Large v2 - Swahili -> EN

2 runs

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Documents

🔗WHATSAPP_audio_from_918764022384_to_113275925092502.wav

Transcription

Sean Blagsvedt

Whisper v3 - Swahili -> EN

15 runs

Documents

🔗https://drive.google.com/file/d/1DQpKCg2J_Osq7u-2hsfvc6R9dFndaTqk/view?usp=drive_link

Transcription

Sean Blagsvedt

Azure ASR (Swahili)

2 runs

Transcribe mp3, WhatsApp audio + wavs with OpenAI's Whisper or AI4Bharat / Bhashini ASR models. Optionally translate to any language too.

Documents

🔗https://www.youtube.com/watch?v=7ZrxTFxeyzY

Transcription

Hello ladies and gentlemen and dear viewers are intoxicated. Today we are here to show you how to make a traditional Abyssinian coffee drink before we continue with our show don't forget to like comment subscribe and end our video. As you know coffee is a popular drink in different countries, but the way of cooking and preparation is different from one country to another today we will show you our culture and way of preparing coffee. Many mothers in Eritrea have a habit of waking up and drinking this coffee before doing any activities in many houses. This is not just a drink but a good intention for families and neighbors, whether Christians or Muslims, to unite and enjoy together. So coffee is our way of showing love. So, this is how we want to organize the things for cooking coffee. First we take as many coffee beans as we want and then we put them in a mehra fet container to remove any bad coffee beans. Then we burn them as you can see. After roasting the coffee pods according to our culture, the one who makes the coffee is given to smell it and then go and they are ground in many countries. People use the excuse of a steamer but we Habesha use mill and pestle to grind. Make sure that these grains are not too soft and they are not powdery so that they settle well when drinking, as you can see our grains are well ground in our country. Many people, especially those from the lowlands, put ginger in their coffee. First we wash the jube and ours which is a clay pot for cooking coffee and then we put our ground coffee in the jabana. Then we put water according to the number of people who will drink and then we put the water in the feneno which is the stove. Bar. After picking and brewing our coffee, we put a vertical press so that the coffee settles down and we put an elevator so that it is not too fast. Now you can prepare three. Coffee is prepared 3 times famously as awel kalti and baraka. Many people drink up to 3 times. Some reach 4 times or even 5 times.

Computational Mama aka Ambika

Whisper v3 (with english translation)

53 runs

Documents

🔗https://drive.google.com/file/d/1DQpKCg2J_Osq7u-2hsfvc6R9dFndaTqk/view?usp=drive_link

Transcription

Computational Mama aka Ambika

Whisper v2 (auto detect)

0 runs

Documents

🔗https://drive.google.com/file/d/1DQpKCg2J_Osq7u-2hsfvc6R9dFndaTqk/view?usp=drive_link

Transcription

Computational Mama aka Ambika

Conformer Hindi (ai4bharat)

32 runs

Documents

🔗https://drive.google.com/file/d/1DQpKCg2J_Osq7u-2hsfvc6R9dFndaTqk/view?usp=drive_link

Computational Mama aka Ambika

Chirp/USM (Google)

47 runs

Documents

🔗https://drive.google.com/file/d/1DQpKCg2J_Osq7u-2hsfvc6R9dFndaTqk/view?usp=drive_link

Transcription

Computational Mama aka Ambika

Deepgram

43 runs

Documents

🔗https://drive.google.com/file/d/1DQpKCg2J_Osq7u-2hsfvc6R9dFndaTqk/view?usp=drive_link

Transcription

Computational Mama aka Ambika

Whisper Hindi Large v2 (Bhashini)

59 runs

Documents

🔗https://drive.google.com/file/d/1DQpKCg2J_Osq7u-2hsfvc6R9dFndaTqk/view?usp=drive_link

Transcription

Computational Mama aka Ambika

Azure - Hindi (Microsoft)

28 runs

Documents

🔗https://drive.google.com/file/d/1DQpKCg2J_Osq7u-2hsfvc6R9dFndaTqk/view?usp=drive_link

Transcription

Computational Mama aka Ambika

Seamless4MT (facebook)

45 runs

Documents

🔗https://drive.google.com/file/d/1DQpKCg2J_Osq7u-2hsfvc6R9dFndaTqk/view?usp=drive_link

Transcription

Whisper Large v2 - Kannada

39 runs

Documents

🔗3_audio_from_918247443697_to_112808001793652.wav

Transcription

Chirp - Kannada

17 runs

Documents

🔗3_audio_from_918247443697_to_112808001793652.wav

Transcription

Azure - Kannada

17 runs

Documents

🔗3_audio_from_918247443697_to_112808001793652.wav

Transcription

Swahili Speech Recognition & Translation via Google Chirp & Translate

21 runs

Documents

🔗https://www.youtube.com/watch?v=7ZrxTFxeyzY

Transcription

hello ladies and gentlemen and dear viewers of the mele show today we are here to show you how to make a traditional Ethiopian coffee drink before we continue with our show don't forget to like comment subscribe and share our video

as you know coffee is a popular drink in different countries but the way to cook and prepare it is different from one country to another today we will show our culture and way of preparing coffee many mothers in Eritrea have the habit of waking up and drinking this coffee before doing any activities in In many houses, this coffee is not just a drink, but a good intention of the family and neighbors, whether Christians or Muslims, to support

and having fun together, so coffee is a way of showing love to us, so this is how we prepare things for cooking coffee, first we take the coffee beans as much as we want, then we put them in a meshrafat container to remove any bad coffee beans, and then we roast them as you can see after roasting the coffee beans coffee according to our culture

what is made of coffee is given and smelled then the beans are ground in many countries people use a steam grinder but we Ethiopians use a mill and pestle to grind make sure these beans are not ground too much so they are not powdery so that they settle well when drinking as you can see our beans are well ground in our country people many especially those in the lower levels put

These ginger first we wash our jebena which is a clay pot for cooking coffee then we put all the ground coffee in the jebena then we put water according to the number of people who will drink it then we put the jebena in the farnelo which is the stove

after picking and brewing our coffee, we put the jebena vertically so that the coffee settles down and we put a lift so that it is brewed quickly, after a while we put the jebena in a slightly drizzling mode, now you can prepare the coffee beans

Coffee is prepared three times famously as aol 80 cal and baraka many people drink up to three times

some reach four times the famous dereja or even five times

a salte, it's a lot, I just want to meet again next time, goodbye

Bhojpuri Speech Recognition (using Gates/Ekstep)

119 runs

This is one of the few Bhojpuri ASR models available based on: https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-bhojpuri-bhom-60
Transcribe mp3, WhatsApp audio + wavs. Optionally translate to any language too.

Documents

🔗https://www.youtube.com/watch?v=WK7rEMCVsGE

Transcription

The Packers have spoken about the work of the Katalka Laka Laka Cola In the age of Taki, the past tense of the farmer, the farmer, the farmer, the farmer, the farmer, whose nails would be tightened, would have been able to defeat the country The farmer worked the fields and the farmers took the soil and cultivated it in a little sack until they took the soil out of the pond Whoever remains is not played with clay or divorced from the clay. The above issue is not understood by Didi Hardajd Lava Bhiyarpi Ka Ka Rile Ghar Alawala Thana Kalyanpur Park Kalyanpur Districtpur Beechanpar Sadidi Sabh Yon Rana Ranai Devi Wuri Jika Sanhayatakasghapur Lyanpur Kalaur Rakha Rubi Chamaran Ke Heane DidiParichay To Bahut Achcha DaniyaAb Eme Kon Kon Samaan Lagat Serhue Khididi If you don't have enough fertilizer, five kilograms of fertilizer or chiva fertilizer, put it in. Put ten kilos of rotten cow. We need a hoe to mix it. See Dairiyuah. We need a hoe to mix it Anyu lagidid lo lagi balt kah yo orvate lage di chaari jarleo lagi di ya sa kahsv vo rov me lagap j yahi me pani dhag ke patava ya sa to ladi savariye ke lagi didi yahi basvake inside panitwaal tomati green rahi nammi rahi from the planting period benefits malia kaha lagara khi menoborovar green disee also VK lahagaghakhnahi t nia ga khi dagara tak whip g augra in put la rover also cut to be that both cut the sama ka ha dakta tani kinche se moisture found hindi saw Now put the sack on both sides and put the soil on both sides. Fill the hole with soil on both sides and see the hole in the pond The bamboo in we put sakarkhatardal only in the water poured the water inside the j saw the didias folded and here we feed now put a fertilizer we add o now dig the this issome fertilizer mavlea khd laes ki de day da mav The Madyan Jewish leaders in the Kamla Se Kadav Khade gave the Mabadar Mess in the Katpan Lap in the Palar Paval in the Samat Khamar Kamada I saw the deep bank sister put water in the pot and put the seeds in it after twenty-four hours. Thikabhaiya we will come after twenty-four hours. Didi came after twenty-four hours The twenty-four hours left to walk around or twenty-four hours is that twenty-four hours has passed and the next process is the same So after cutting two equal patties and two at the bottom, you have to cut two equal patches and two at the bottom Pacharit seeds Balahka Ghida Jhignikural Tekrla also stopped Didiya me kayaro fe dekhi Didi somewhere in the seeds put now this public committee picked up the medal clay Kahlagala sa bhayaur se dhant diyat Didi ye sri je raja yank diya ta Didi ye ja paje bhaiye I will not water the seedlings until they are known. I will plant the seeds. I request all the sisters who do not have land to cultivate the sack and eat the vegetables He benefits from the precautions to be taken then sisters to be careful to save the goats now sisters CE precautions to save the goats to raise the goats thank you all sisters brothers well tell me to farm in sacks Thank you very much to Degi and you

Speech Recognition and Translation

6 runs

Documents

🔗https://www.youtube.com/watch?v=PdNZ9ip0qjg

Transcription

Speech Recognition and Translation

8 runs

Documents

🔗4dc062a8-b080-45c5-b538-cb30c854c83c.wav

Transcription

Speech Recognition and Translation

1 runs

Documents

🔗https://www.youtube.com/watch?v=L-yHhIq3sE0&list=PL4aOhrbpcqyYGrLHMyZIgVNej2pa53uac&index=14

Transcription

1
00:00:00,000 --> 00:00:10,080
Hi, I'm Sean, one of the founders here at GUI, and I wanted to give you a demo today

2
00:00:10,080 --> 00:00:14,940
of how to use one of our recipes, a face in any scene.

3
00:00:14,940 --> 00:00:17,180
So I just go ahead and click on this.

4
00:00:17,180 --> 00:00:21,220
And so the scenario that I'd like you to imagine with us is, let's imagine, you know, rather

5
00:00:21,220 --> 00:00:25,980
than trying to do stuff with Elon Musk, we are working for a travel agency, and we've

6
00:00:24,000 --> 00:00:30,000
a travel agency and we've got a spokesperson and we want to show that person basically all over the

7
00:00:30,000 --> 00:00:33,680
country in a variety of locations, which is expensive because you got to send that person

8
00:00:33,680 --> 00:00:39,600
out, you got to do a photo shoot, and so what I'll do is I can just drag in a picture. So I have here

9
00:00:39,600 --> 00:00:46,320
Lana, AI-generated spokesperson that I've drafted right here, and then I can just take any other

10
00:00:46,320 --> 00:00:51,040
quote. So I'll just copy in another one right here, which is basically a beautiful woman to

11
00:00:48,000 --> 00:00:49,760
We have another one right here,

12
00:00:49,760 --> 00:00:51,160
which is basically a beautiful woman

13
00:00:51,160 --> 00:00:54,640
to the Grand Tetons in Hawaii or Wyoming

14
00:00:54,640 --> 00:00:56,560
and award-winning landscape photographer.

15
00:00:56,560 --> 00:00:59,080
And then you literally just do those two

16
00:00:59,080 --> 00:01:00,320
and then hit submit.

17
00:01:01,400 --> 00:01:04,120
What happens now is we're looking for this face

18
00:01:04,120 --> 00:01:07,000
and then we basically go ahead and we craft out

19
00:01:07,000 --> 00:01:10,160
or mask out that particular face, we readjust it.

20
00:01:10,160 --> 00:01:12,040
And then boom, we've got this picture

21
00:01:12,040 --> 00:01:15,200
of Lana hanging out at the Grand Tetons.

22
00:01:15,200 --> 00:01:17,040
You can go ahead and download that

23
00:01:12,000 --> 00:01:15,200
of Lana hanging out at the Grand Tetons.

24
00:01:15,200 --> 00:01:17,020
You can go ahead and download that

25
00:01:17,020 --> 00:01:18,120
and we can change anything else.

26
00:01:18,120 --> 00:01:19,440
So if we wanna say, well, no,

27
00:01:19,440 --> 00:01:21,400
she's not at the Grand Tetons,

28
00:01:21,400 --> 00:01:25,080
she's in something like Maroon Bells,

29
00:01:25,080 --> 00:01:28,080
another famous American destination that I've never been to.

30
00:01:29,400 --> 00:01:30,240
We can put that up

31
00:01:30,240 --> 00:01:32,120
and then you'll notice the same thing happens.

32
00:01:32,120 --> 00:01:33,560
And it's in about nine seconds.

33
00:01:33,560 --> 00:01:37,160
We do the same face repositioning, same face masking.

34
00:01:37,160 --> 00:01:39,040
We put that in and then we do a little bit of cleanup

35
00:01:39,040 --> 00:01:40,880
at the end with JPFK.

36
00:01:36,000 --> 00:01:39,520
masking, we put that in and then we do a little bit of cleanup at the end with

37
00:01:39,520 --> 00:01:44,920
JPF CAD. And so this is an example of a four-stage recipe that hopefully anybody

38
00:01:44,920 --> 00:01:49,960
can go ahead and use just by uploading a picture of a person and any text they

39
00:01:49,960 --> 00:01:54,320
want. So we hope you enjoy it and we look forward to seeing what you make with it.

40
00:01:54,320 --> 00:01:57,440
Thanks so much!

Speech Recognition and Translation

1 runs

Documents

🔗https://www.youtube.com/watch?v=L-yHhIq3sE0&list=PL4aOhrbpcqyYGrLHMyZIgVNej2pa53uac&index=14

Transcription

Hi, I'm Sean, one of the founders here at GUI. And I wanted to give you a demo today of how to use one of our recipes, a face in any scene. So just go ahead and click on this. And so the scenario that I'd like you to imagine with us is let's imagine, you know, rather than trying to do stuff with Elon Musk, we are working for a travel agency and we've got a spokesperson and we want to show that person basically all over the country in a variety of locations. Which is expensive because you got to send that person out, you got to do a photo shoot. And so what I'll do is I can just drag in a picture. So I have here Lana, AI generated spokesperson that I've drafted right here. And then I can just take any other quote. So I'll just copy in another one right here, which is basically a beautiful woman to the grand Tetons in Hawaii or Wyoming and award-winning landscape photographer. And then you literally just do those two and then hit submit. What happens now is we're looking for this face and then we basically go ahead and we craft out or mask out that particular face. We readjust it and then boom, we've got this picture of Lana hanging out at the grand Tetons. You can go ahead and download that and we can change anything else. So if we want to say, well, no, she's not at the Grand Tetons, you know, she's in something like Maroon Bells, another famous American destination that I've never been to. We can put that up and then you'll notice the same thing happens. In about nine seconds, we do the same face repositioning, same face masking, we put that in and then we do a little bit of cleanup at the end with JPF CAD. And so this is an example of a four stage recipe that hopefully anybody can go ahead and use just by uploading a picture of a person and any text they want. So we hope you enjoy it and we look forward to seeing what you make with it. Thanks so much.

Speech Recognition and Translation

1 runs

Documents

🔗https://www.youtube.com/watch?v=Cgd_Cjxyme4&list=PL3LYCEMgJ1urYQcVZEj1D9VlupHW3hlcT&index=2

Transcription

So there are two ways to look at this. The first is the thing that matters most to leaders, which is how is this going to help the company financially, productivity-wise. And the other is in terms of having a better workforce, a better managed workforce, a more productive, more cooperative and efficient workforce. So these are the two main reasons why I would say that leaders have to care about mental health at work. But there are also other reasons that if you explore further into the reasons why, you know, if you look at generational differences and other things, the younger workforce is more interested in looking for jobs or being employed in jobs where they find meaning in their work. It's not really about salaries or having stability alone anymore. Of course, that's very important. But meaning is very important to them, being able to do something that's filled with purpose with meaning that gives them satisfaction right so that's something that's changing with the generations and Today if the younger workforce if they are not happy they don't feel obliged to stick with a company They find something else to do Something non-traditional, you know, gig economy, this and that. So there are different ways of looking at it and if you look at it from an HR perspective in terms of retaining your good employees, controlling turnover, you know, employee turnover, making sure that your workforce that you already have is efficient, they're happy, you know, you say they say a happy worker is a productive worker. And so there are several reasons why I would say leaders should care about mental health. It just depends on the lens through which you're looking.

Examples: Speech

Chichewa ASR via MMS-Large + Google Translate

Kikuyu via MMS Large and GhanaNLP for Speech Reco & Trans

Whisper Large v3 - Kannada

Seamless M4T Kannada -> EN

Google Cloud V1 - Swahili -> EN

Seamless M4T - Swahili -> EN

Whisper Large v2 - Swahili -> EN

Whisper v3 - Swahili -> EN

Azure ASR (Swahili)

Whisper v3 (with english translation)

Whisper v2 (auto detect)

Conformer Hindi (ai4bharat)

Chirp/USM (Google)

Deepgram

Whisper Hindi Large v2 (Bhashini)

Azure - Hindi (Microsoft)

Seamless4MT (facebook)

Whisper Large v2 - Kannada

Chirp - Kannada

Azure - Kannada

Swahili Speech Recognition & Translation via Google Chirp & Translate

Bhojpuri Speech Recognition (using Gates/Ekstep)

Speech Recognition and Translation

Speech Recognition and Translation

Speech Recognition and Translation

Speech Recognition and Translation

Speech Recognition and Translation

GET STARTED

LEARN

DEVELOPERS

SOCIAL

CONNECT

EXTRAS